ai model report

Is tencent/Hy3 safe to load?

CyberXYZ rates tencent/Hy3 CLEAN. No version-matched advisories and no malicious packages. It depends on 399 tracked packages, and 6 carry advisories. It does not require trust_remote_code.

View on HuggingFace

// posture
advisories 100provenance 75resolution 100xyz safety 100load safety 100supply chain 100scanner trust 100code execution 70
fig. 01 — posture on eight axes, 100 is clean. Weakest: code execution at 70.
// the finding
not scoredno advisory applies to a version this model pinsCLEAN

INFOconfig.json was authored against transformers 5.6.0, which has known advisories. Consumers normally install a current version — this only bites if you pin for reproducibility.

1 more finding on this model.

Author
tencent
Task
text-generation
Loader
transformers
License
apache-2.0
Downloads
837,193
Remote code
not required
// dependencies

29 direct, 19 with findings, 389 reachable

PackageEvidenceAdvisoriesWorst
transformersdirect, runtime24none pinned
torchdirect, runtime13none pinned
Create a free accountto see all 399 dependencies, which versions are pinned, and what to change.
// what changed
  • HIGHvector new2026-09-09
  • MEDIUMvector new2026-09-09
  • MEDIUMrisk level raised (unknown to medium)2026-09-09
// questions
Is tencent/Hy3 safe to load?

CyberXYZ does not call a model safe in absolute terms. It rates tencent/Hy3 CLEAN. No version-matched advisories and no malicious packages. That covers its dependencies and how it loads, not every file it ships, so treat any check that did not run as unverified and check the exact files before you load them.

What does tencent/Hy3 depend on?

CyberXYZ tracks 399 dependencies for tencent/Hy3, 29 of them direct. 6 carry advisories. They include transformers and torch. A free account lists all of them.

Does tencent/Hy3 run code when it loads?

HuggingFace does not mark tencent/Hy3 as requiring trust_remote_code. That says nothing about the format of its weight files, which model_load_safety checks per file.

How do I check tencent/Hy3 before loading it?

Run the xyz MCP tool model_load_safety on tencent/Hy3 to get a verdict on its weight files before you load them, or search it in CyberXYZ Check at https://cyberxyz.io/check?q=tencent%2FHy3.


Risk computed 2026-11-14 at 13:05 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.

Model risk is computed from the model's declared and observed Python dependencies and the code it ships. If a finding is wrong, tell us.